• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.28-36
• /
• 2022

As port structures are exposed to various extreme external loads such as wind (typhoons), sea waves, or collision with ships; it is important to evaluate the structural safety periodically. To monitor the port structure, especially the rubber fender, a fender segmentation system using a vision sensor and deep learning method has been proposed in this study. For fender segmentation, a new deep learning network that improves the encoder-decoder framework with the receptive field block convolution module inspired by the eccentric function of the human visual system into the DenseNet format has been proposed. In order to train the network, various fender images such as BP, V, cell, cylindrical, and tire-types have been collected, and the images are augmented by applying four augmentation methods such as elastic distortion, horizontal flip, color jitter, and affine transforms. The proposed algorithm has been trained and verified with the collected various types of fender images, and the performance results showed that the system precisely segmented in real time with high IoU rate (84%) and F1 score (90%) in comparison with the conventional segmentation model, VGG16 with U-net. The trained network has been applied to the real images taken at one port in Republic of Korea, and found that the fenders are segmented with high accuracy even with a small dataset.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.104-123
• /
• 2022

Style transfer based on neural network provides very high quality results by reflecting the high level structural characteristics of images, and thereby has recently attracted great attention. This paper deals with the problem of resolution limitation due to GPU memory in performing such neural style transfer. We can expect that the gradient operation for style transfer based on partial image, with the aid of the fixed size of receptive field, can produce the same result as the gradient operation using the entire image. Based on this idea, each component of the style transfer loss function is analyzed in this paper to obtain the necessary conditions for partitioning and padding, and to identify, among the information required for gradient calculation, the one that depends on the entire input. By structuring such information for using it as auxiliary constant input for partition-based gradient calculation, this paper develops a recursive algorithm for super high-resolution image style transfer. Since the proposed method performs style transfer by partitioning input image into the size that a GPU can handle, it can perform style transfer without the limit of the input image resolution accompanied by the GPU memory size. With the aid of such super high-resolution support, the proposed method can provide a unique style characteristics of detailed area which can only be appreciated in super high-resolution style transfer.

• Journal of Korean Academy of Nursing
• /
• v.31 no.5
• /
• pp.781-792
• /
• 2001

Professional nurse Autonomy is an essential attribute of a discipline striving for full professional status. Purpose: This study was to clarify the concept of professional nurse autonomy to provide basic data needed for development of professional autonomy enhancing strategies. Method: This study use the process of Walker & Avante's concept analysis based on Wade's research (1999), and field data of 21 nurses. Results: Professional nurse autonomy is defined as competency and creative performance of the professional nurse in practice, to decide independently or interdependently nursing activities and to be had accountable for results of decisions, that reflect advocacy and caring. It was identified that critical attributes include responsible discretionary decision making, collegial interdependence, initiative, creativity, and caring, advocacy, cooperative relationship with clients, receptive capacity to others, activeness, self confidence, and devotion and responsibility to their profession. Antecedents include personal characteristics, educational background, experience and structural characteristics that enhance professional nurse autonomy. Consequences of professional nurse autonomy are feelings of self-efficacy, empowerment, job satisfaction, reduction of intention to leave their job. Conclusion: According to these results, it is recommended that the curriculum provides an environment for learning professional nurse autonomy, and that is used as basic data to develope strategies to enhance professional autonomy of nurse in practice and it's effects

• Biomolecules & Therapeutics
• /
• v.1 no.1
• /
• pp.37-43
• /
• 1993

Electrical or chemical stimulation of many areas in the brainstem modulates activity of dorsal horn neurons (DHN). This is known to be mediated by a population of bulbospinal neurons. Yet, little is known about responses of DHNs to stimulation of the caudal ventrolateral medulla (CVLM). Thus, the purpose of the present study is to see if there is any change in activity of DHNs when CVLM is stimulated electrically. Thirty-one DHNs were recorded from dorsal horn of the spinal cord. Fourteen DHNs (45%) were classified as wide dynamic range neurons and 9 (19%) were high threshold cells, and 4 (13%) and 4 (13%) were deep and low threshold neurons, respectively. Among 31 neurons tested for responses to stimulation of CVLM, 21 DHNs (68%) were inhibited by the electrical stimulation of CVLM ($200{\mu}A,\;100{\mu}s$ duration, 100 Hz), and 9 cells (39%) did not show any change in neuronal activity. One neuron was excited by the stimulation. The electrical stimulation of CVLM not only inhibited spontaneous activity of DHNs but also inhibited evoked responses of DHNs to somatic stimulation in the receptive field. These data suggest that CVLM is one of the pain-modulatory areas that control transmission of ascending information of noxious input to the brain from the spinal cord.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.617-629
• /
• 2001

The mathematical models for the receptive field of simple cells in the human visual system have been developed in the areas of psychophysics, physiology and neuroscience. The various models used in the fields of digital image processing and computer vision include Gator complex, Gaussian derivatives and Hermite functions. In this paper, the effective widths for the models are derived based on the space-frequency uncertainty principle. The center frequency and parameters related to the models are determined in accordance with the human visual filters, and resultant bandwidths are analyzed. Furthermore, the characteristics of space and frequency for the models is analyzed and compared to the experimental data obtained from psychophysics.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.8
• /
• pp.1117-1128
• /
• 2002

This study suggests the most efficient teaching method by using multi-media. Based on the outcome of the engineering study, the multi-media and their contents will be applied to teaching methods, at first needing to provide concept and educational expecting effect of them. For multi-media using teaching methods, the study suggests the following 4; (1) teaching method for instructional learning, (2) teaching method for detective learning by guild, (3) teaching method for receptive loaming, (4) teaching method for exploration. Challenges still remained is to examine principles of teaching planning and relevant theories in order to apply the multi-media for the existing education, which should ask teachers in field to select more efficient teaching methods.

• Information and Communications Magazine
• /
• v.9 no.11
• /
• pp.34-36
• /
• 1992

여러 개의 문자(혹은 여러 개의 자소로 구성된 한개의 문자)를 인식할때에는 문자(혹은 자소) 상호간에 영향을 미쳐서 오인식이 발생할 가능성이 높다. 개개의 숫자인식에 기초한 숫자열 인식이나, 개개의 자소인식을 바탕으로한 필기체 한글인식이 그 좋은 보기일 것이다. 예를 들어 단순한 한글 '그'를 Neocognitron으로 인식한다고 생각해 보자, 조합 가능한 글자를 모두 기억시키려면 방대한 규모의 회로가 필요하므로 현실적으로 불가능하다. 따라서 기본 자소(자음 14개, 모음 10개)를 인식하도록 학습시키고 이를 바탕으로 한글을 인식하는 것이 효율적이다. 이때, 회로의 각 세포가 보는 receptive field가 유한하여 '?'의 끝 세로부분 'I'가 '?'에 영향을 미쳐서 '?'로 인식된다 즉, 자소간의 섭동에 의해 '그'가 '고'로 인식되는 것이다. 이와같은 예는 '니'가 '넉'으로, '41'이 '4H'로 인식되는 등 매우 많지만 그 해결에 대한 연구는 거의 없다. 이 논문에서는 필기체 한글 자소를 인식하는 Necognitron외에 자소간의 섭동현상을 제거하기 위한 high-level constraint 회로를 Lotka-Volterra동역학에 기초하여 설계하였다. 이로써 off-line필기체 한글인식을 보다 효과적으로 할 수 있음을 컴퓨터 시뮬레이션으로 보인다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.11
• /
• pp.852-858
• /
• 1991

An adaptive hierarchical classifier(AHCL) for Korean character recognition using a neural net is designed. This classifier has two neural nets: USACL (Unsupervised Adaptive Classifier) and SACL (Supervised Adaptive Classifier). USACL has the input layer and the output layer. The input layer and the output layer are fully connected. The nodes in the output layer are generated by the unsupervised and nearest neighbor learning rule during learning. SACL has the input layer, the hidden layer and the output layer. The input layer and the hidden layer arefully connected, and the hidden layer and the output layer are partially connected. The nodes in the SACL are generated by the supervised and nearest neighbor learning rule during learning. USACL has pre-attentive effect, which perform partial search instead of full search during SACL classification to enhance processing speed. The input of USACL and SACL is a directional edge feature with a directional receptive field. In order to test the performance of the AHCL, various multi-font printed Hangul characters are used in learning and testing, and its processing its speed and and classification rate are compared with the conventional LVQ(Learning Vector Quantizer) which has the nearest neighbor learning rule.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.10
• /
• pp.1469-1478
• /
• 2015

In this paper, The methodology of Type-2 fuzzy set-based Radial Basis Function Neural Network(T2RBFNN) is proposed for Sewage Treatment Process and the simulator is developed for application to the real-world sewage treatment plant by using the proposed model. The proposed model has robust characteristic than conventional RBFNN. architecture of network consist of three layers such as input layer, hidden layer and output layer of RBFNN, and Type-2 fuzzy set is applied to receptive field in contrast with conventional radial basis function. In addition, the connection weights of the proposed model are defined as linear polynomial function, and then are learned through Back-Propagation(BP). Type reduction is carried out by using Karnik and Mendel(KM) algorithm between hidden layer and output layer. Sewage treatment data obtained from real-world sewage treatment plant is employed to evaluate performance of the proposed model, and their results are analyzed as well as compared with those of conventional RBFNN.